Three-dimensional (3D) depth imaging systems and methods for automatically determining shipping container fullness based on imaging templates

Three-dimensional (3D) depth imaging systems and methods are disclosed for automatically determining shipping container fullness based on imaging templates. A 3D-depth camera captures 3D image data of a shipping container located in a predefined search space during a shipping container loading session. A container fullness application (app) receives the 3D image data and determines therefrom a 3D container point cloud representative of a shipping container. An imaging template that defines a 3D template point cloud corresponding to a shipping container type of the shipping container is loaded into memory. A fullness value of the shipping container is determined based on a 3D mapping that is generated from alignment of a 3D container front portion of the 3D container point cloud with a 3D template front portion of the 3D template point cloud. The container fullness application may determine the imaging template based on the 3D image data received from the 3D depth camera using a machine learning model trained with 3D Image data defining a plurality of shipping container types which takes as an input the 3D image data and outputs the shipping container type allowing the relevant imaging template to be loaded based on the shipping container type. The 3D depth imaging system may include executing closest point algorithm that generates a 3D match score based on distances between a set of 3D points of the 3D container point cloud and a second set OF 3D points of the template point cloud. The imaging template may be a non-point cloud imaging template and loading the imaging template includes converting, the non-point cloud template to the 3D template point cloud.